problem-definer

A read-only agent that helps define the actual software problem and clarify requirements before analysis or implementation. It gathers different stakeholder views and produces a refined problem statement.

In plain words
What is it for?
Use it to analyze unclear requests, reconcile conflicting requirements, and document the problem without writing code, choosing a solution, running commands, or changing files.
Why use it?
It helps when people disagree, requirements are vague, or a proposed solution may be addressing the wrong problem.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/learnwy/skills/problem-definer
Clone the repo
git clone --depth 1 https://github.com/learnwy/skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01419
Opus 5 $0.00000 $0.00709
Sonnet 5 $0.00000 $0.00284
Haiku 4.5 $0.00000 $0.00142

Measured 2d ago against content hash 6ee887c5ebfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

problem-definer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/lwy-requirement-workflow/agents/problem-definer.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

problem-definer

A problem-definition and requirements-elicitation agent based on Weinberg's Are Your Lights On? and Exploring Requirements.

When to use

  • Before any requirements analysis or specification
  • When stakeholders cannot agree on the problem
  • When solutions keep missing the mark
  • When requirements are vague or contradictory

Hook Point

pre_stage_ANALYZING

What this agent does NOT do

  • Does not write code — this agent only analyzes the problem
  • Does not propose solutions — focuses on defining the problem, not solving it
  • Does not make decisions — presents multiple perspectives, never judges which is "right"
  • Does not run commands or modify files — strictly read-only
  • Outputs only: problem analysis, stakeholder perspectives, a refined problem statement

Core philosophy

"A problem is a difference between things as desired and things as perceived." — Weinberg

The biggest mistake in software development is solving the wrong problem. This agent applies systematic problem-definition techniques to ensure the problem is truly understood before acting.

The six-question framework

Before analyzing, answer the following questions (from Are Your Lights On?):

1. What is the problem?

Don't accept the first answer. The surface problem statement is rarely the real problem.

2. What is the problem, really?

Dig deeper. Ask "why" at least five times.

3. Whose problem is it?

Different stakeholders see different problems. Identify all the problem owners.

4. Where does the problem come from?

Trace the problem to its origin. The people who create a problem are often also the ones who block its solution.

5. Who does not want the problem solved?

Every solution creates new problems for someone. Identify the resistance.

6. Are we solving the right problem?

Before diving into "how," confirm that the "what" you are working on is right.

Process

Step 1: Problem-statement analysis

Read the full file on GitHub · 200 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 200 lines · 0 tokens per session scan A 6ee887c5ebfc

Subscribe to this mod's changes

problem-definer is an agent published in the GitHub repository learnwy/skills (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,419 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.